Signal Processing and Machine Learning with Differential Privacy

By Anand D. Sarwate, Kamalika Chaudhuri. 2013

202 citations recorded by the source corpus.

Private companies, government entities, and institutions such as hospitals routinely gather vast amounts of digitized personal information about the individuals who are their customers, clients, or patients. Much of this information is private or sensitive, and a key technological challenge for the future is how to design systems and processing techniques for drawing inferences from this large-scale data while maintaining the privacy and security of the data and individual identities. Individuals are often willing to share data, especially for purposes such as public health, but they expect that their identity or the fact of their participation will not be disclosed. In recent years, there have been a number of privacy models and privacy-preserving data analysis algorithms to answer these challenges. In this article, we will describe the progress made on differentially private machine learning and signal processing.

Subfields: Artificial Intelligence, Computer Networks and Communications, Privacy & Security, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Privacy & Security

In Signal Processing

Citations in the corpus

Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning (2017, background): “Several works have adopted DP as an efficient defense mechanism such as [5, 7, 11, 12, 18, 23, 24, 37, 53, 60, 65, 72, 86].”
Learning Privately over Distributed Features: An ADMM Sharing Approach (2019, background): “As-sumption 2.2 comes from Zhang and Zhu (2016b) and Assumption 2.3 comes from Zhang and Zhu (2016b) and Sarwate and Chaudhuri (2013).”
cpSGD: Communication-efficient and differentially-private distributed SGD (2018, background): “Providing rigorous privacy guarantees for machine learning applications has been an area of active recent interest [6, 35, 31].”
Marginal Release Under Local Differential Privacy (2017, background): “It has been a topic of inquiry for diverse research communities including theory [35], data management [25], machine learning [33], and systems/programming languages [27].”
The Value of Collaboration in Convex Machine Learning with Differential Privacy (2019, background): “A natural way for alleviating privacy concerns is to deploy privacy-enabled ML using differential privacy (DP) [16]–[19].”
Trustworthy artificial intelligence (2020, methodology): “…has proposed several approaches to protect people ’ s privacy during the training and operation of an AI, like adding noise to data and models (Sarwate and Chaudhuri 2013), the use of trusted execution environments (Tramer and Boneh 2019), or federated learning for AI model training (Smith…”
Privacy preservation in federated learning: An insightful survey from the GDPR perspective (2020, methodology): “Differential privacy technique has beenwidely employed in various ML algorithms such as linear and logistic regression [19], Support Vector Machine (SVM) [102] and deep learning [20, 1], as well as in ML-based applications such as data mining [39] and signal processing with continuous data [108].”
Differentially Private Data Publishing and Analysis: A Survey (2017, background): “[7] focused on privacy preserving for continuous data to solve the problems in signal”
Privacy-preserving deep learning (2015, methodology): “It has been applied to boosting [21], principal component analysis [10], linear and logistic regression [8, 57], support vector machines [41], risk minimization [9, 53], and continuous data processing [43].”
The Large Margin Mechanism for Differentially Private Maximization (2014, background): “There has been a large amount of work on differential privacy for a wide range of statistical and machine learning tasks over the last decade [6, 30, 13, 21, 33, 24, 1]; for overviews, see [18] and [29].”
A Stability-based Validation Procedure for Differentially Private Machine Learning (2013, background): “…over the past few years as there has been a large explosion of theoretical and experimental work on differentially private algorithms for statistical and machine-learning tasks [10, 2, 15, 19, 27, 28, 3] – see [24] for a recent survey of machine learning methods with a focus on continuous data.”
Stochastic gradient descent with differentially private updates (2013, background): “Sarwate and Chaudhuri provide a tutorial from a signal processing perspective [8].”
Differential Privacy in the Wild: A Tutorial on Current Practices & Open Challenges (2016, unknown): “, regression/classification [1, 5, 14, 23, 39, 41, 42] and itemset mining [29, 44]).”
Privacy-preserving Analysis of Correlated Data (2016, background): “Suppose t > log(1/πΘ)gΘ , and ∆t = exp(−tgΘ) πΘ .”
Collecting and Analyzing Data from Smart Device Users with Local Differential Privacy (2016, background): “Hence, since its proposal in 2003 it had attracted much attention from various research communities in computer science, including theory [10], machine learning [18], data management [21], and systems [19].”
Blockchain-Based Privacy Preserving Deep Learning (2018, background): “2) Techniques based on diﬀerential privacy have been proposed to guarantee the conﬁdentiality of personal data while training a diﬀerentially-private model [18], [19], [20], [21], [22], [23], [24], [25].”